Dynamic relational inference models uncover potential complex system interactions, enabling trajectory prediction and improving the interpretability of underlying system dynamics. However, the existing models cannot a...
详细信息
Dynamic relational inference models uncover potential complex system interactions, enabling trajectory prediction and improving the interpretability of underlying system dynamics. However, the existing models cannot accurately infer the structural evolution trends and complete dynamic processes of temporal networks. Additionally, when uncertain noisy data are input, more serious graph noise problems, including redundant and noisy edges, occur, undermining the stability of interaction inference and reducing the accuracy of trajectory prediction. Therefore, a masked graph autoencoder-based multi-agent dynamic relational inference (MGAE-MDRI) trajectory prediction model is proposed herein. The mask reconstruction module is integrated into MDRI, where the partial edges of the interaction graph, representing multi-agent dynamic evolution, are masked through sampling. The reconstruction strategy leverages path and degree considerations to mitigate the impact of graph noise on the network topology. Furthermore, a graph attention network-based path sampler with a preference random walk is introduced, effectively combining network topology and node attribute features to construct a topologically weighted degree matrix and assign optimal mask sampling weights to neighboring nodes. Experiments conducted on four standard public datasets demonstrate that MGAE-MDRI outperforms the state-of-theart models, achieving better trajectory prediction robustness and for complex multi-agent systems.
masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operati...
详细信息
masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferior representations for downstream evaluations. To address this issue, we propose a novel SGP method termed Robust masked graph autoencoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space. Through both theoretical and empirical analyses, we have discovered that performing a joint mask-then-reconstruct strategy in both latent feature and raw data spaces could yield improved stability and performance. To this end, we elaborately design a masked latent feature completion scheme, which predicts latent features of masked nodes under the guidance of high-order sample correlations that are hard to be observed from the raw data perspective. Specifically, we first adopt a latent feature predictor to predict the masked latent features from the visible ones. Next, we encode the raw data of masked samples with a momentum graph encoder and subsequently employ the resulting representations to improve the predicted results through latent feature matching. Extensive experiments on seventeen datasets have demonstrated the effectiveness and robustness of RARE against state-of-the-art (SOTA) competitors across three downstream tasks.
Biomedical evidence has demonstrated the relevance of microRNA (miRNA) dysregulation in complex human diseases, and determining the relationship between miRNAs and diseases can aid in the early detection and preventio...
详细信息
Biomedical evidence has demonstrated the relevance of microRNA (miRNA) dysregulation in complex human diseases, and determining the relationship between miRNAs and diseases can aid in the early detection and prevention of diseases. Traditional biological experimental methods have the disadvantages of high cost and low efficiency, which are well compensated by computational methods. However, many computational methods have the challenge of excessively focusing on the neighbor relationship, ignoring the structural information of the graph, and belittling the redundant information of the graph structure. This study proposed a computational model based on a graph-masking autoencoder named MGAEMDA. MGAEMDA is an asymmetric framework in which the encoder maps partially observed graphs into latent representations. The decoder reconstructs the masked structural information based on the edge and node levels and combines it with linear matrices to obtain the result. The empirical results on the two datasets reveal that the MGAEMDA model performs better than its counterparts. We also demonstrated the predictive performance of MGAEMDA using a case study of four diseases, and all the top 30 predicted miRNAs were validated in the database, providing further evidence of the excellent performance of the model.
Analysing source code using deep learning aids compile-time decisions affecting performance in embedded devices. We propose Deep-Codegraph, a general graph-based language model, which learns patterns to identify bette...
详细信息
ISBN:
(纸本)9783031702389;9783031702396
Analysing source code using deep learning aids compile-time decisions affecting performance in embedded devices. We propose Deep-Codegraph, a general graph-based language model, which learns patterns to identify better compilation strategies, optimal hardware configurations and software transformations. DCG includes i) A large-scale dataset containing over 100k graphs. ii) A graph neural network to implement a graph-based language model. iii) A self-supervised pre-training framework leveraging masked graph autoencoders. The performance of DCG is evaluated on two downstream tasks: heterogeneous device mapping and thread block size prediction. DCG outperforms previous graph-based state-of-the-art improving previous results by 3%.
Self-supervised learning (SSL) has been demonstrated to be effective in pre-training models that can be generalized to various downstream tasks. graphautoencoder (GAE), an increasingly popular SSL approach on graphs,...
详细信息
ISBN:
(纸本)9781450394079
Self-supervised learning (SSL) has been demonstrated to be effective in pre-training models that can be generalized to various downstream tasks. graphautoencoder (GAE), an increasingly popular SSL approach on graphs, has been widely explored to learn node representations without ground-truth labels. However, recent studies show that existing GAE methods could only perform well on link prediction tasks, while their performance on classification tasks is rather limited. This limitation casts doubt on the generalizability and adoption of GAE. In this paper, for the first time, we show that GAE can generalize well to both link prediction and classification scenarios, including node-level and graph-level tasks, by redesigning its critical building blocks from the graph masking perspective. Our proposal is called Self-Supervised graphautoencoder-S2GAE, which unleashes the power of GAEs with minimal yet nontrivial efforts. Specifically, instead of reconstructing the whole input structure, we randomly mask a portion of edges and learn to reconstruct these missing edges with an effective masking strategy and an expressive decoder network. Moreover, we theoretically prove that S2GAE could be regarded as an edge-level contrastive learning framework, providing insights into why it generalizes well. Empirically, we conduct extensive experiments on 21 benchmark datasets across link prediction and node&graph classification tasks. The results validate the superiority of S2GAE against state-of-the-art generative and contrastive methods. This study demonstrates the potential of GAE as a universal representation learner on graphs. Our code is publicly available at https://***/qiaoyu-tan/S2GAE
暂无评论